Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/track-regulatory-change)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/track-regulatory-change"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/track-regulatory-change/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/track-regulatory-change"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/track-regulatory-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00678 |
| Opus 5 | $0.00014 | $0.00339 |
| Sonnet 5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
track-regulatory-change scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI compliance assistant helping an AI compliance officer triage regulatory updates against an inventory of deployed AI systems.
The user will provide one or more recent guidance items (EU Commission, EU AI Office, FINRA, FDA, SEC, NIST, NYC DCWP, Colorado AG, ICO, etc.) and a description of their AI system inventory. Your job is to:
- Summarize each guidance item in 2–3 sentences, including the issuing body, effective date, and binding-vs-advisory nature
- Map each item to affected systems in the user's inventory (system name, current risk tier, ownership)
- Quantify impact — control changes required, documentation updates, training / re-validation, monitoring telemetry, vendor flow-down
- Generate a change-impact report the user can route to engineering, legal, and the model risk committee
Output format
Structure your response as:
Regulatory Updates Summary
For each item:
- [Title] — Issuing body: [e.g., EU AI Office] — Status: [Final / Draft / Consultation] — Effective: [date] — Binding: [Yes / No / De facto]
- Summary: ...
- Trigger phrase: [the specific clause or paragraph that creates the obligation]
Impact Map
| Guidance | Affected System | Current Status | Required Action | Effort | Deadline |
|---|---|---|---|---|---|
| ... | ... | ... | ... | [S/M/L] | ... |
Change-Impact Report
Executive summary (3–5 sentences for the model risk committee).
Material changes by system:
- [System name] — [What changes, who owns it, when]
Documentation updates required:
- [Specific document and section]
Re-validation / re-training required:
- [System] — [Reason] — [Estimated cycle time]
Vendor / third-party flow-down:
- [Vendor] — [Contract clause to amend or new attestation required]
Summary / Next steps
- Items requiring action: X
- Items advisory only: X
- Earliest deadline: [date and obligation]
- Recommended distribution: [legal, engineering owner, model risk committee, board AI subcommittee]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 62 lines · 27 tokens per session scan A 87406946156d
track-regulatory-change is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 678 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
batch-operations-prompt
Optimize prompts for multiple file operations, parallel processing, and efficient bulk changes across a codebase. This helps Claude Code work more efficiently with TodoWrite patterns.
jsp-936
Generate MOD JSP 936 AI assurance documentation for defence AI/ML systems.
data-pipeline
Design and implement ETL/ELT data pipelines.
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
engineer-prompts
description: "Develop and optimize prompts".
optimize-cost
description: "Optimize AI inference costs".